Table 2.

Diagnostic performance of different machine learning classifiers in validation cohort

Model	AUC	Accuracy	Sensitivity	Specificity	PPV	NPV	F1 score
XGBoost	0.81 (0.72–0.90)	0.68	0.81	0.72	0.80	0.59	0.80
LightGBM	0.78 (0.69–0.88)	0.69	0.72	0.76	0.77	0.60	0.73
Logistic	0.72 (0.61–0.83)	0.64	0.79	0.61	0.72	0.55	0.75
RandomForest	0.74 (0.70–0.86)	0.67	0.76	0.64	0.74	0.59	0.74

AUC, area under curve; LightGBM, light gradient boosting; NPV, negative predictive value; PPV, positive predictive value; XGBoost, eXtreme Gradient Boosting